Faster Convergence to Cooperative Policy by Autonomous Detection of Interference States in Multiagent Reinforcement Learning
نویسندگان
چکیده
In this paper, we propose a method for ameliorating the state-space explosion that can occur in the context of multiagent reinforcement learning. In our method, an agent considers other agents’ states only when they interfere with each other in attaining their goals. Our idea is that the initial state-space of each agent does not include information about other spaces. Agents then automatically expand their state-space if they detect interference states. We adopt the information theory measure of entropy to detect the interference states for which agents should consider the state information of other agents. We demonstrate the advantage of our method with respect to the efficiency of global convergence.
منابع مشابه
A Multiagent Reinforcement Learning algorithm to solve the Community Detection Problem
Community detection is a challenging optimization problem that consists of searching for communities that belong to a network under the assumption that the nodes of the same community share properties that enable the detection of new characteristics or functional relationships in the network. Although there are many algorithms developed for community detection, most of them are unsuitable when ...
متن کاملLearning to Communicate and Act in Cooperative Multiagent Systems using Hierarchical Reinforcement Learning
In this paper, we address the issue of rational communication behavior among autonomous agents. We extend our previously reported cooperative hierarchical reinforcement learning (HRL) algorithm to include communication decision and propose a new multiagent HRL algorithm, called COM-Cooperative HRL. In this algorithm, at specific levels of the hierarchy, called cooperation levels, a group of sub...
متن کاملMultiagent reinforcement learning: algorithm converging to Nash equilibrium in general-sum discounted stochastic games
Reinforcement learning turned out a technique that allowed robots to ride a bicycle, computers to play backgammon on the level of human world masters and solve such complicated tasks of high dimensionality as elevator dispatching. Can it come to rescue in the next generation of challenging problems like playing football or bidding on virtual markets? Reinforcement learning that provides a way o...
متن کاملState Elimination in Accelerated Multiagent Reinforcement Learning
This paper presents a novel algorithm of Multiagent Reinforcement Learning called State Elimination in Accelerated Multiagent Reinforcement Learning (SEA-MRL), that successfully produces faster learning without incorporating internal knowledge or human intervention such as reward shaping, transfer learning, parameter tuning, and even heuristics, into the learning system. Since the learning spee...
متن کاملThe Dynamics of Reinforcement Learning in Cooperative Multiagent Systems
Reinforcement learning can provide a robust and natural means for agents to learn how to coordinate their action choices in multiagent systems. We examine some of the factors that can influence the dynamics of the learning process in such a setting. We first distinguish reinforcement learners that are unaware of (or ignore) the presence of other agents from those that explicitly attempt to lear...
متن کامل